Noometry

Model comparison

Gemini 2.5 Flash-Lite vs Grok 3

Grok 3 is the stronger model overall, scoring 39.9 to 37.0 on the Noometry Index.

Last verified . 27 shared benchmarks.

Gemini 2.5 Flash-Lite Google

37.0

Rank #211 Confirmed

Grok 3 xAI

39.9

Rank #157 Confirmed

Summary

  • They share 27 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 2 categories and Grok 3 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok 3 leads 46.2 to 32.5.
  • The biggest single-benchmark swing is GPQA (HELM): 30.9% for Gemini 2.5 Flash-Lite and 65% for Grok 3.

Side by side

Gemini 2.5 Flash-LiteGrok 3
ProviderGooglexAI
Noometry Index37.039.9
Released2025-06-172025-04-09
WeightsProprietaryProprietary
Context window1.05M—
Max output66K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.40—
Results tracked3340

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Grok 3 leads

Gemini 2.5 Flash-Lite: 38.5 (#173), Grok 3: 41.9 (#115)

BenchmarkGemini 2.5 Flash-LiteGrok 3
WeirdML35.2%37.2%
LMArena Coding13731432
Aider Polyglot—53.3%
ALE-Bench325.9—

Agentic & Tool Use Grok 3 leads

Gemini 2.5 Flash-Lite: 28.0 (#96), Grok 3: 30.5 (#76)

BenchmarkGemini 2.5 Flash-LiteGrok 3
Berkeley Function Calling Leaderboard36.9%—
BALROG—29.5%

Reasoning Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 22.2 (#205), Grok 3: 13.7 (#333)

BenchmarkGemini 2.5 Flash-LiteGrok 3
Kagi LLM Benchmark40.5%61.3%
LMArena Hard Prompts13771434
Epoch Capabilities Index133.94138.33
ARC-AGI-2—0%
SimpleBench—36.1%
ARC-AGI-1—5.5%
DTBench62.8%—
LMCA18.1%—

Math Too close to call

Gemini 2.5 Flash-Lite: 38.0 (#144), Grok 3: 38.0 (#145)

BenchmarkGemini 2.5 Flash-LiteGrok 3
Omni-MATH48%46.4%
LMArena Math13731391
OTIS Mock AIME 2024-2025—55.6%
MATH Level 5—88.7%
FrontierMath (Feb 2025 set)—3.8%
FrontierMath Tier 4 (v1)—0%

Knowledge Grok 3 leads

Gemini 2.5 Flash-Lite: 32.5 (#210), Grok 3: 46.2 (#82)

BenchmarkGemini 2.5 Flash-LiteGrok 3
MMLU-Pro53.7%78.8%
Vectara Hallucination Rate3.3%5.8%
GPQA (HELM)30.9%65%
LMArena Expert13731421
GPQA Diamond—75.8%
Confabulations—14.2%

Multimodal Not comparable

Gemini 2.5 Flash-Lite: 29.1 (#114), Grok 3: —

BenchmarkGemini 2.5 Flash-LiteGrok 3
LMArena Vision1198—
VPCT30%—

Multilingual Grok 3 leads

Gemini 2.5 Flash-Lite: 49.3 (#134), Grok 3: 52.3 (#87)

BenchmarkGemini 2.5 Flash-LiteGrok 3
LMArena Non-English13691410
LMArena Chinese14041448
LMArena French13881460
LMArena German13891431
LMArena Japanese13591387
LMArena Korean13601373
LMArena Russian13731416
LMArena Spanish13961417

Instruction Following Grok 3 leads

Gemini 2.5 Flash-Lite: 70.0 (#168), Grok 3: 75.0 (#73)

BenchmarkGemini 2.5 Flash-LiteGrok 3
IFEval81%88.4%
LMArena Instruction Following13671409

Long Context Grok 3 leads

Gemini 2.5 Flash-Lite: 33.3 (#262), Grok 3: 38.7 (#192)

BenchmarkGemini 2.5 Flash-LiteGrok 3
Fiction.LiveBench47.2%58.3%
LMArena Longer Query13731439

Writing & Preference Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 56.8 (#135), Grok 3: 55.8 (#141)

BenchmarkGemini 2.5 Flash-LiteGrok 3
LMArena Text13791426
LMArena Creative Writing13671414
WildBench81.8%84.9%
LMArena Multi-Turn13661425
Short-Story Creative Writing—76.4%
EQ-Bench Creative Writing—1186

Frequently asked questions

Is Gemini 2.5 Flash-Lite better than Grok 3?

Grok 3 is the stronger model overall, scoring 39.9 to 37.0 on the Noometry Index.

Is Gemini 2.5 Flash-Lite or Grok 3 better for coding?

Grok 3 scores higher on coding benchmarks: 41.9 versus 38.5 in the Noometry coding category.

How many benchmarks do Gemini 2.5 Flash-Lite and Grok 3 share?

27 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Grok 3 has 40.

Related comparisons

Go deeper